--- library_name: transformers language: - aa - am - ar - arc - bcw - byn - cop - daa - de - dsh - en - es - fr - gde - gnd - ha - hbo - he - hig - irk - jpa - kab - ker - kqp - ktb - kxc - lln - lme - meq - mfh - mfi - mfk - mif - mpg - mqb - mt - muy - oar - om - pbi - phn - pt - rif - sgw - shi - shy - so - sur - syc - syr - taq - thv - ti - tig - tmc - tmh - tmr - ttr - tzm - wal - xed - zgh tags: - translation - opus-mt-tc-bible license: apache-2.0 model-index: - name: opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa results: - task: name: Translation acm-deu type: translation args: acm-deu dataset: name: flores200-devtest type: flores200-devtest args: acm-deu metrics: - name: BLEU type: bleu value: 17.6 - name: chr-F type: chrf value: 0.48947 - task: name: Translation acm-eng type: translation args: acm-eng dataset: name: flores200-devtest type: flores200-devtest args: acm-eng metrics: - name: BLEU type: bleu value: 28.5 - name: chr-F type: chrf value: 0.56799 - task: name: Translation acm-fra type: translation args: acm-fra dataset: name: flores200-devtest type: flores200-devtest args: acm-fra metrics: - name: BLEU type: bleu value: 26.1 - name: chr-F type: chrf value: 0.53577 - task: name: Translation acm-por type: translation args: acm-por dataset: name: flores200-devtest type: flores200-devtest args: acm-por metrics: - name: BLEU type: bleu value: 23.9 - name: chr-F type: chrf value: 0.52441 - task: name: Translation acm-spa type: translation args: acm-spa dataset: name: flores200-devtest type: flores200-devtest args: acm-spa metrics: - name: BLEU type: bleu value: 18.2 - name: chr-F type: chrf value: 0.46985 - task: name: Translation amh-deu type: translation args: amh-deu dataset: name: flores200-devtest type: flores200-devtest args: amh-deu metrics: - name: BLEU type: bleu value: 12.6 - name: chr-F type: chrf value: 0.41553 - task: name: Translation amh-eng type: translation args: amh-eng dataset: name: flores200-devtest type: flores200-devtest args: amh-eng metrics: - name: BLEU type: bleu value: 22.5 - name: chr-F type: chrf value: 0.49333 - task: name: Translation amh-fra type: translation args: amh-fra dataset: name: flores200-devtest type: flores200-devtest args: amh-fra metrics: - name: BLEU type: bleu value: 17.8 - name: chr-F type: chrf value: 0.44890 - task: name: Translation amh-por type: translation args: amh-por dataset: name: flores200-devtest type: flores200-devtest args: amh-por metrics: - name: BLEU type: bleu value: 16.5 - name: chr-F type: chrf value: 0.43771 - task: name: Translation amh-spa type: translation args: amh-spa dataset: name: flores200-devtest type: flores200-devtest args: amh-spa metrics: - name: BLEU type: bleu value: 12.8 - name: chr-F type: chrf value: 0.39526 - task: name: Translation apc-deu type: translation args: apc-deu dataset: name: flores200-devtest type: flores200-devtest args: apc-deu metrics: - name: BLEU type: bleu value: 16.0 - name: chr-F type: chrf value: 0.47480 - task: name: Translation apc-eng type: translation args: apc-eng dataset: name: flores200-devtest type: flores200-devtest args: apc-eng metrics: - name: BLEU type: bleu value: 28.1 - name: chr-F type: chrf value: 0.56075 - task: name: Translation apc-fra type: translation args: apc-fra dataset: name: flores200-devtest type: flores200-devtest args: apc-fra metrics: - name: BLEU type: bleu value: 24.6 - name: chr-F type: chrf value: 0.52325 - task: name: Translation apc-por type: translation args: apc-por dataset: name: flores200-devtest type: flores200-devtest args: apc-por metrics: - name: BLEU type: bleu value: 22.9 - name: chr-F type: chrf value: 0.51055 - task: name: Translation apc-spa type: translation args: apc-spa dataset: name: flores200-devtest type: flores200-devtest args: apc-spa metrics: - name: BLEU type: bleu value: 17.2 - name: chr-F type: chrf value: 0.45634 - task: name: Translation arz-deu type: translation args: arz-deu dataset: name: flores200-devtest type: flores200-devtest args: arz-deu metrics: - name: BLEU type: bleu value: 14.1 - name: chr-F type: chrf value: 0.45844 - task: name: Translation arz-eng type: translation args: arz-eng dataset: name: flores200-devtest type: flores200-devtest args: arz-eng metrics: - name: BLEU type: bleu value: 22.7 - name: chr-F type: chrf value: 0.52534 - task: name: Translation arz-fra type: translation args: arz-fra dataset: name: flores200-devtest type: flores200-devtest args: arz-fra metrics: - name: BLEU type: bleu value: 21.8 - name: chr-F type: chrf value: 0.50336 - task: name: Translation arz-por type: translation args: arz-por dataset: name: flores200-devtest type: flores200-devtest args: arz-por metrics: - name: BLEU type: bleu value: 20.0 - name: chr-F type: chrf value: 0.48741 - task: name: Translation arz-spa type: translation args: arz-spa dataset: name: flores200-devtest type: flores200-devtest args: arz-spa metrics: - name: BLEU type: bleu value: 15.8 - name: chr-F type: chrf value: 0.44516 - task: name: Translation hau-eng type: translation args: hau-eng dataset: name: flores200-devtest type: flores200-devtest args: hau-eng metrics: - name: BLEU type: bleu value: 23.4 - name: chr-F type: chrf value: 0.48137 - task: name: Translation hau-fra type: translation args: hau-fra dataset: name: flores200-devtest type: flores200-devtest args: hau-fra metrics: - name: BLEU type: bleu value: 17.2 - name: chr-F type: chrf value: 0.42981 - task: name: Translation hau-por type: translation args: hau-por dataset: name: flores200-devtest type: flores200-devtest args: hau-por metrics: - name: BLEU type: bleu value: 15.7 - name: chr-F type: chrf value: 0.41385 - task: name: Translation hau-spa type: translation args: hau-spa dataset: name: flores200-devtest type: flores200-devtest args: hau-spa metrics: - name: BLEU type: bleu value: 11.7 - name: chr-F type: chrf value: 0.37800 - task: name: Translation heb-deu type: translation args: heb-deu dataset: name: flores200-devtest type: flores200-devtest args: heb-deu metrics: - name: BLEU type: bleu value: 22.8 - name: chr-F type: chrf value: 0.53482 - task: name: Translation heb-eng type: translation args: heb-eng dataset: name: flores200-devtest type: flores200-devtest args: heb-eng metrics: - name: BLEU type: bleu value: 38.0 - name: chr-F type: chrf value: 0.63368 - task: name: Translation heb-fra type: translation args: heb-fra dataset: name: flores200-devtest type: flores200-devtest args: heb-fra metrics: - name: BLEU type: bleu value: 32.6 - name: chr-F type: chrf value: 0.58417 - task: name: Translation heb-por type: translation args: heb-por dataset: name: flores200-devtest type: flores200-devtest args: heb-por metrics: - name: BLEU type: bleu value: 30.7 - name: chr-F type: chrf value: 0.57140 - task: name: Translation kab-eng type: translation args: kab-eng dataset: name: flores200-devtest type: flores200-devtest args: kab-eng metrics: - name: BLEU type: bleu value: 10.0 - name: chr-F type: chrf value: 0.32121 - task: name: Translation mlt-eng type: translation args: mlt-eng dataset: name: flores200-devtest type: flores200-devtest args: mlt-eng metrics: - name: BLEU type: bleu value: 51.1 - name: chr-F type: chrf value: 0.73415 - task: name: Translation mlt-fra type: translation args: mlt-fra dataset: name: flores200-devtest type: flores200-devtest args: mlt-fra metrics: - name: BLEU type: bleu value: 35.8 - name: chr-F type: chrf value: 0.61626 - task: name: Translation mlt-spa type: translation args: mlt-spa dataset: name: flores200-devtest type: flores200-devtest args: mlt-spa metrics: - name: BLEU type: bleu value: 21.8 - name: chr-F type: chrf value: 0.50534 - task: name: Translation som-eng type: translation args: som-eng dataset: name: flores200-devtest type: flores200-devtest args: som-eng metrics: - name: BLEU type: bleu value: 17.7 - name: chr-F type: chrf value: 0.42764 - task: name: Translation som-fra type: translation args: som-fra dataset: name: flores200-devtest type: flores200-devtest args: som-fra metrics: - name: BLEU type: bleu value: 14.4 - name: chr-F type: chrf value: 0.39536 - task: name: Translation som-por type: translation args: som-por dataset: name: flores200-devtest type: flores200-devtest args: som-por metrics: - name: BLEU type: bleu value: 14.1 - name: chr-F type: chrf value: 0.39440 - task: name: Translation som-spa type: translation args: som-spa dataset: name: flores200-devtest type: flores200-devtest args: som-spa metrics: - name: BLEU type: bleu value: 10.0 - name: chr-F type: chrf value: 0.35321 - task: name: Translation tir-eng type: translation args: tir-eng dataset: name: flores200-devtest type: flores200-devtest args: tir-eng metrics: - name: BLEU type: bleu value: 11.6 - name: chr-F type: chrf value: 0.37119 - task: name: Translation amh-deu type: translation args: amh-deu dataset: name: flores101-devtest type: flores_101 args: amh deu devtest metrics: - name: BLEU type: bleu value: 11.5 - name: chr-F type: chrf value: 0.39890 - task: name: Translation amh-eng type: translation args: amh-eng dataset: name: flores101-devtest type: flores_101 args: amh eng devtest metrics: - name: BLEU type: bleu value: 21.0 - name: chr-F type: chrf value: 0.47357 - task: name: Translation amh-fra type: translation args: amh-fra dataset: name: flores101-devtest type: flores_101 args: amh fra devtest metrics: - name: BLEU type: bleu value: 16.2 - name: chr-F type: chrf value: 0.43155 - task: name: Translation amh-por type: translation args: amh-por dataset: name: flores101-devtest type: flores_101 args: amh por devtest metrics: - name: BLEU type: bleu value: 15.1 - name: chr-F type: chrf value: 0.42109 - task: name: Translation amh-spa type: translation args: amh-spa dataset: name: flores101-devtest type: flores_101 args: amh spa devtest metrics: - name: BLEU type: bleu value: 11.5 - name: chr-F type: chrf value: 0.38003 - task: name: Translation ara-deu type: translation args: ara-deu dataset: name: flores101-devtest type: flores_101 args: ara deu devtest metrics: - name: BLEU type: bleu value: 20.4 - name: chr-F type: chrf value: 0.51110 - task: name: Translation ara-fra type: translation args: ara-fra dataset: name: flores101-devtest type: flores_101 args: ara fra devtest metrics: - name: BLEU type: bleu value: 29.7 - name: chr-F type: chrf value: 0.56934 - task: name: Translation ara-por type: translation args: ara-por dataset: name: flores101-devtest type: flores_101 args: ara por devtest metrics: - name: BLEU type: bleu value: 28.2 - name: chr-F type: chrf value: 0.55727 - task: name: Translation ara-spa type: translation args: ara-spa dataset: name: flores101-devtest type: flores_101 args: ara spa devtest metrics: - name: BLEU type: bleu value: 19.5 - name: chr-F type: chrf value: 0.48350 - task: name: Translation hau-eng type: translation args: hau-eng dataset: name: flores101-devtest type: flores_101 args: hau eng devtest metrics: - name: BLEU type: bleu value: 21.6 - name: chr-F type: chrf value: 0.46804 - task: name: Translation hau-fra type: translation args: hau-fra dataset: name: flores101-devtest type: flores_101 args: hau fra devtest metrics: - name: BLEU type: bleu value: 15.9 - name: chr-F type: chrf value: 0.41827 - task: name: Translation hau-spa type: translation args: hau-spa dataset: name: flores101-devtest type: flores_101 args: hau spa devtest metrics: - name: BLEU type: bleu value: 11.5 - name: chr-F type: chrf value: 0.37201 - task: name: Translation heb-eng type: translation args: heb-eng dataset: name: flores101-devtest type: flores_101 args: heb eng devtest metrics: - name: BLEU type: bleu value: 36.6 - name: chr-F type: chrf value: 0.62422 - task: name: Translation mlt-eng type: translation args: mlt-eng dataset: name: flores101-devtest type: flores_101 args: mlt eng devtest metrics: - name: BLEU type: bleu value: 49.1 - name: chr-F type: chrf value: 0.72390 - task: name: Translation mlt-fra type: translation args: mlt-fra dataset: name: flores101-devtest type: flores_101 args: mlt fra devtest metrics: - name: BLEU type: bleu value: 34.7 - name: chr-F type: chrf value: 0.60840 - task: name: Translation mlt-por type: translation args: mlt-por dataset: name: flores101-devtest type: flores_101 args: mlt por devtest metrics: - name: BLEU type: bleu value: 31.8 - name: chr-F type: chrf value: 0.59863 - task: name: Translation amh-eng type: translation args: amh-eng dataset: name: ntrex128 type: ntrex128 args: amh-eng metrics: - name: BLEU type: bleu value: 15.0 - name: chr-F type: chrf value: 0.42042 - task: name: Translation amh-fra type: translation args: amh-fra dataset: name: ntrex128 type: ntrex128 args: amh-fra metrics: - name: BLEU type: bleu value: 10.8 - name: chr-F type: chrf value: 0.37274 - task: name: Translation amh-spa type: translation args: amh-spa dataset: name: ntrex128 type: ntrex128 args: amh-spa metrics: - name: BLEU type: bleu value: 12.1 - name: chr-F type: chrf value: 0.38306 - task: name: Translation hau-eng type: translation args: hau-eng dataset: name: ntrex128 type: ntrex128 args: hau-eng metrics: - name: BLEU type: bleu value: 26.1 - name: chr-F type: chrf value: 0.50349 - task: name: Translation hau-fra type: translation args: hau-fra dataset: name: ntrex128 type: ntrex128 args: hau-fra metrics: - name: BLEU type: bleu value: 15.8 - name: chr-F type: chrf value: 0.41837 - task: name: Translation hau-por type: translation args: hau-por dataset: name: ntrex128 type: ntrex128 args: hau-por metrics: - name: BLEU type: bleu value: 15.3 - name: chr-F type: chrf value: 0.40851 - task: name: Translation hau-spa type: translation args: hau-spa dataset: name: ntrex128 type: ntrex128 args: hau-spa metrics: - name: BLEU type: bleu value: 18.5 - name: chr-F type: chrf value: 0.43376 - task: name: Translation heb-deu type: translation args: heb-deu dataset: name: ntrex128 type: ntrex128 args: heb-deu metrics: - name: BLEU type: bleu value: 17.7 - name: chr-F type: chrf value: 0.49482 - task: name: Translation heb-eng type: translation args: heb-eng dataset: name: ntrex128 type: ntrex128 args: heb-eng metrics: - name: BLEU type: bleu value: 31.3 - name: chr-F type: chrf value: 0.59241 - task: name: Translation heb-fra type: translation args: heb-fra dataset: name: ntrex128 type: ntrex128 args: heb-fra metrics: - name: BLEU type: bleu value: 24.0 - name: chr-F type: chrf value: 0.52180 - task: name: Translation heb-por type: translation args: heb-por dataset: name: ntrex128 type: ntrex128 args: heb-por metrics: - name: BLEU type: bleu value: 23.2 - name: chr-F type: chrf value: 0.51248 - task: name: Translation mlt-spa type: translation args: mlt-spa dataset: name: ntrex128 type: ntrex128 args: mlt-spa metrics: - name: BLEU type: bleu value: 30.9 - name: chr-F type: chrf value: 0.57078 - task: name: Translation som-deu type: translation args: som-deu dataset: name: ntrex128 type: ntrex128 args: som-deu metrics: - name: BLEU type: bleu value: 11.0 - name: chr-F type: chrf value: 0.39394 - task: name: Translation som-eng type: translation args: som-eng dataset: name: ntrex128 type: ntrex128 args: som-eng metrics: - name: BLEU type: bleu value: 24.3 - name: chr-F type: chrf value: 0.49187 - task: name: Translation som-fra type: translation args: som-fra dataset: name: ntrex128 type: ntrex128 args: som-fra metrics: - name: BLEU type: bleu value: 15.1 - name: chr-F type: chrf value: 0.41236 - task: name: Translation som-por type: translation args: som-por dataset: name: ntrex128 type: ntrex128 args: som-por metrics: - name: BLEU type: bleu value: 15.2 - name: chr-F type: chrf value: 0.41550 - task: name: Translation som-spa type: translation args: som-spa dataset: name: ntrex128 type: ntrex128 args: som-spa metrics: - name: BLEU type: bleu value: 17.6 - name: chr-F type: chrf value: 0.43278 - task: name: Translation tir-eng type: translation args: tir-eng dataset: name: ntrex128 type: ntrex128 args: tir-eng metrics: - name: BLEU type: bleu value: 12.5 - name: chr-F type: chrf value: 0.37185 - task: name: Translation tir-spa type: translation args: tir-spa dataset: name: ntrex128 type: ntrex128 args: tir-spa metrics: - name: BLEU type: bleu value: 10.2 - name: chr-F type: chrf value: 0.34985 - task: name: Translation amh-eng type: translation args: amh-eng dataset: name: tatoeba-test-v2021-03-30 type: tatoeba_mt args: amh-eng metrics: - name: BLEU type: bleu value: 59.5 - name: chr-F type: chrf value: 0.70202 - task: name: Translation ara-deu type: translation args: ara-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: ara-deu metrics: - name: BLEU type: bleu value: 41.7 - name: chr-F type: chrf value: 0.61039 - task: name: Translation ara-eng type: translation args: ara-eng dataset: name: tatoeba-test-v2020-07-28 type: tatoeba_mt args: ara-eng metrics: - name: BLEU type: bleu value: 42.8 - name: chr-F type: chrf value: 0.60134 - task: name: Translation ara-fra type: translation args: ara-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: ara-fra metrics: - name: BLEU type: bleu value: 38.8 - name: chr-F type: chrf value: 0.56120 - task: name: Translation ara-spa type: translation args: ara-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: ara-spa metrics: - name: BLEU type: bleu value: 43.7 - name: chr-F type: chrf value: 0.62567 - task: name: Translation heb-deu type: translation args: heb-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: heb-deu metrics: - name: BLEU type: bleu value: 42.4 - name: chr-F type: chrf value: 0.63131 - task: name: Translation heb-eng type: translation args: heb-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: heb-eng metrics: - name: BLEU type: bleu value: 49.2 - name: chr-F type: chrf value: 0.64960 - task: name: Translation heb-fra type: translation args: heb-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: heb-fra metrics: - name: BLEU type: bleu value: 46.3 - name: chr-F type: chrf value: 0.64348 - task: name: Translation heb-por type: translation args: heb-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: heb-por metrics: - name: BLEU type: bleu value: 43.2 - name: chr-F type: chrf value: 0.63350 - task: name: Translation kab-eng type: translation args: kab-eng dataset: name: tatoeba-test-v2021-03-30 type: tatoeba_mt args: kab-eng metrics: - name: BLEU type: bleu value: 27.8 - name: chr-F type: chrf value: 0.44646 - task: name: Translation kab-spa type: translation args: kab-spa dataset: name: tatoeba-test-v2020-07-28 type: tatoeba_mt args: kab-spa metrics: - name: BLEU type: bleu value: 23.4 - name: chr-F type: chrf value: 0.41526 - task: name: Translation mlt-eng type: translation args: mlt-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: mlt-eng metrics: - name: BLEU type: bleu value: 51.0 - name: chr-F type: chrf value: 0.66653 - task: name: Translation multi-multi type: translation args: multi-multi dataset: name: tatoeba-test-v2020-07-28-v2023-09-26 type: tatoeba_mt args: multi-multi metrics: - name: BLEU type: bleu value: 34.0 - name: chr-F type: chrf value: 0.51369 - task: name: Translation hau-eng type: translation args: hau-eng dataset: name: newstest2021 type: wmt-2021-news args: hau-eng metrics: - name: BLEU type: bleu value: 15.5 - name: chr-F type: chrf value: 0.43744 --- # opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa ## Table of Contents - [Model Details](#model-details) - [Uses](#uses) - [Risks, Limitations and Biases](#risks-limitations-and-biases) - [How to Get Started With the Model](#how-to-get-started-with-the-model) - [Training](#training) - [Evaluation](#evaluation) - [Citation Information](#citation-information) - [Acknowledgements](#acknowledgements) ## Model Details Neural machine translation model for translating from Afro-Asiatic languages (afa) to unknown (deu+eng+fra+por+spa). This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train). **Model Description:** - **Developed by:** Language Technology Research Group at the University of Helsinki - **Model Type:** Translation (transformer-big) - **Release**: 2024-05-29 - **License:** Apache-2.0 - **Language(s):** - Source Language(s): aar acm afb amh apc ara arc arq arz bcw byn cop daa dsh gde gnd hau hbo heb hig irk jpa kab ker kqp ktb kxc lln lme meq mfh mfi mfk mif mlt mpg mqb muy oar orm pbi phn rif sgw shi shy som sur syc syr taq thv tig tir tmc tmh tmr ttr tzm wal xed zgh - Target Language(s): deu eng fra por spa - Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<< - **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip) - **Resources for more information:** - [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/afa-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-29) - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train) - [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian) - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/) - [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1) - [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/) This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>deu<<` ## Uses This model can be used for translation and text-to-text generation. ## Risks, Limitations and Biases **CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.** Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). ## How to Get Started With the Model A short example code: ```python from transformers import MarianMTModel, MarianTokenizer src_text = [ ">>eng<< Anta i ak-d-yennan ur yerbiḥ ara Tom?", ">>fra<< Iselman d aɣbalu axatar i wučči n yemdanen." ] model_name = "pytorch-models/opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa" tokenizer = MarianTokenizer.from_pretrained(model_name) model = MarianMTModel.from_pretrained(model_name) translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True)) for t in translated: print( tokenizer.decode(t, skip_special_tokens=True) ) # expected output: # Who told you that he didn't? # L'eau est une source importante de nourriture pour les gens. ``` You can also use OPUS-MT models with the transformers pipelines, for example: ```python from transformers import pipeline pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-afa-deu_eng_fra_por_spa") print(pipe(">>eng<< Anta i ak-d-yennan ur yerbiḥ ara Tom?")) # expected output: Who told you that he didn't? ``` ## Training - **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge)) - **Pre-processing**: SentencePiece (spm32k,spm32k) - **Model Type:** transformer-big - **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip) - **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train) ## Evaluation * [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/afa-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-29) * test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt) * test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/afa-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt) * benchmark results: [benchmark_results.txt](benchmark_results.txt) * benchmark output: [benchmark_translations.zip](benchmark_translations.zip) | langpair | testset | chr-F | BLEU | #sent | #words | |----------|---------|-------|-------|-------|--------| | ara-deu | tatoeba-test-v2021-08-07 | 0.61039 | 41.7 | 1209 | 8371 | | ara-eng | tatoeba-test-v2021-08-07 | 5.430 | 0.0 | 10305 | 76975 | | ara-fra | tatoeba-test-v2021-08-07 | 0.56120 | 38.8 | 1569 | 11066 | | ara-spa | tatoeba-test-v2021-08-07 | 0.62567 | 43.7 | 1511 | 9708 | | heb-deu | tatoeba-test-v2021-08-07 | 0.63131 | 42.4 | 3090 | 25101 | | heb-eng | tatoeba-test-v2021-08-07 | 0.64960 | 49.2 | 10519 | 77427 | | heb-fra | tatoeba-test-v2021-08-07 | 0.64348 | 46.3 | 3281 | 26123 | | heb-por | tatoeba-test-v2021-08-07 | 0.63350 | 43.2 | 719 | 5335 | | mlt-eng | tatoeba-test-v2021-08-07 | 0.66653 | 51.0 | 203 | 1165 | | amh-eng | flores101-devtest | 0.47357 | 21.0 | 1012 | 24721 | | amh-fra | flores101-devtest | 0.43155 | 16.2 | 1012 | 28343 | | amh-por | flores101-devtest | 0.42109 | 15.1 | 1012 | 26519 | | ara-deu | flores101-devtest | 0.51110 | 20.4 | 1012 | 25094 | | ara-fra | flores101-devtest | 0.56934 | 29.7 | 1012 | 28343 | | ara-por | flores101-devtest | 0.55727 | 28.2 | 1012 | 26519 | | ara-spa | flores101-devtest | 0.48350 | 19.5 | 1012 | 29199 | | hau-eng | flores101-devtest | 0.46804 | 21.6 | 1012 | 24721 | | hau-fra | flores101-devtest | 0.41827 | 15.9 | 1012 | 28343 | | heb-eng | flores101-devtest | 0.62422 | 36.6 | 1012 | 24721 | | mlt-eng | flores101-devtest | 0.72390 | 49.1 | 1012 | 24721 | | mlt-fra | flores101-devtest | 0.60840 | 34.7 | 1012 | 28343 | | mlt-por | flores101-devtest | 0.59863 | 31.8 | 1012 | 26519 | | acm-deu | flores200-devtest | 0.48947 | 17.6 | 1012 | 25094 | | acm-eng | flores200-devtest | 0.56799 | 28.5 | 1012 | 24721 | | acm-fra | flores200-devtest | 0.53577 | 26.1 | 1012 | 28343 | | acm-por | flores200-devtest | 0.52441 | 23.9 | 1012 | 26519 | | acm-spa | flores200-devtest | 0.46985 | 18.2 | 1012 | 29199 | | amh-deu | flores200-devtest | 0.41553 | 12.6 | 1012 | 25094 | | amh-eng | flores200-devtest | 0.49333 | 22.5 | 1012 | 24721 | | amh-fra | flores200-devtest | 0.44890 | 17.8 | 1012 | 28343 | | amh-por | flores200-devtest | 0.43771 | 16.5 | 1012 | 26519 | | apc-deu | flores200-devtest | 0.47480 | 16.0 | 1012 | 25094 | | apc-eng | flores200-devtest | 0.56075 | 28.1 | 1012 | 24721 | | apc-fra | flores200-devtest | 0.52325 | 24.6 | 1012 | 28343 | | apc-por | flores200-devtest | 0.51055 | 22.9 | 1012 | 26519 | | apc-spa | flores200-devtest | 0.45634 | 17.2 | 1012 | 29199 | | arz-deu | flores200-devtest | 0.45844 | 14.1 | 1012 | 25094 | | arz-eng | flores200-devtest | 0.52534 | 22.7 | 1012 | 24721 | | arz-fra | flores200-devtest | 0.50336 | 21.8 | 1012 | 28343 | | arz-por | flores200-devtest | 0.48741 | 20.0 | 1012 | 26519 | | arz-spa | flores200-devtest | 0.44516 | 15.8 | 1012 | 29199 | | hau-eng | flores200-devtest | 0.48137 | 23.4 | 1012 | 24721 | | hau-fra | flores200-devtest | 0.42981 | 17.2 | 1012 | 28343 | | hau-por | flores200-devtest | 0.41385 | 15.7 | 1012 | 26519 | | heb-deu | flores200-devtest | 0.53482 | 22.8 | 1012 | 25094 | | heb-eng | flores200-devtest | 0.63368 | 38.0 | 1012 | 24721 | | heb-fra | flores200-devtest | 0.58417 | 32.6 | 1012 | 28343 | | heb-por | flores200-devtest | 0.57140 | 30.7 | 1012 | 26519 | | mlt-eng | flores200-devtest | 0.73415 | 51.1 | 1012 | 24721 | | mlt-fra | flores200-devtest | 0.61626 | 35.8 | 1012 | 28343 | | mlt-spa | flores200-devtest | 0.50534 | 21.8 | 1012 | 29199 | | som-eng | flores200-devtest | 0.42764 | 17.7 | 1012 | 24721 | | tir-por | flores200-devtest | 2.931 | 0.0 | 1012 | 26519 | | hau-eng | newstest2021 | 0.43744 | 15.5 | 997 | 27372 | | amh-eng | ntrex128 | 0.42042 | 15.0 | 1997 | 47673 | | hau-eng | ntrex128 | 0.50349 | 26.1 | 1997 | 47673 | | hau-fra | ntrex128 | 0.41837 | 15.8 | 1997 | 53481 | | hau-por | ntrex128 | 0.40851 | 15.3 | 1997 | 51631 | | hau-spa | ntrex128 | 0.43376 | 18.5 | 1997 | 54107 | | heb-deu | ntrex128 | 0.49482 | 17.7 | 1997 | 48761 | | heb-eng | ntrex128 | 0.59241 | 31.3 | 1997 | 47673 | | heb-fra | ntrex128 | 0.52180 | 24.0 | 1997 | 53481 | | heb-por | ntrex128 | 0.51248 | 23.2 | 1997 | 51631 | | mlt-spa | ntrex128 | 0.57078 | 30.9 | 1997 | 54107 | | som-eng | ntrex128 | 0.49187 | 24.3 | 1997 | 47673 | | som-fra | ntrex128 | 0.41236 | 15.1 | 1997 | 53481 | | som-por | ntrex128 | 0.41550 | 15.2 | 1997 | 51631 | | som-spa | ntrex128 | 0.43278 | 17.6 | 1997 | 54107 | | tir-eng | tico19-test | 2.655 | 0.0 | 2100 | 56824 | ## Citation Information * Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.) ```bibtex @article{tiedemann2023democratizing, title={Democratizing neural machine translation with {OPUS-MT}}, author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami}, journal={Language Resources and Evaluation}, number={58}, pages={713--755}, year={2023}, publisher={Springer Nature}, issn={1574-0218}, doi={10.1007/s10579-023-09704-w} } @inproceedings{tiedemann-thottingal-2020-opus, title = "{OPUS}-{MT} {--} Building open translation services for the World", author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh}, booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation", month = nov, year = "2020", address = "Lisboa, Portugal", publisher = "European Association for Machine Translation", url = "https://aclanthology.org/2020.eamt-1.61", pages = "479--480", } @inproceedings{tiedemann-2020-tatoeba, title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}", author = {Tiedemann, J{\"o}rg}, booktitle = "Proceedings of the Fifth Conference on Machine Translation", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.wmt-1.139", pages = "1174--1182", } ``` ## Acknowledgements The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/). ## Model conversion info * transformers version: 4.45.1 * OPUS-MT git hash: a0ea3b3 * port time: Mon Oct 7 17:08:30 EEST 2024 * port machine: LM0-400-22516.local